Face Recognition using Fuzzy Neural Network

Face recognition is a biometric tool for authentication and verification, has great emphasis in both research and practical applications. Increased requirement on security, fully automated biometrics on personal identification and verification has received extensive attention over the past few years. In this paper we propose a novel face recognition using Fuzzy Neural network, which is used to extract features from face images by dividing the images into two phase one is of training phase by neural network second is extracting phase done by fuzzy inference system. At first the Complex Wavelet Transform is a tool applied here that uses a dual tree of wavelet filters to find the real and imaginary parts of complex wavelet coefficients. The DT-CWT is, however, less redundant and computationally efficient. Dual Tree methods are based on image at different resolution. Here the DT-CWT is used to convert the entire image into 2-D form and also here Principal Component Analysis which is a linear dimensionality reduction technique is used, that attempt to represent data in lower dimensions, i.e., used to perform the face recognition which means simply it reduces the 2-D form to 1-D form. Finally we have to extract face by comparing features using fuzzy neural networks. At present many methods for image recognition are available but most of them include feature to any type of images. The proposal is divided into two phases: the training phase and the extraction or processing related to type of image. In this paper these two parts of the network one is neural network for training, second is fuzzy inference system which helps us improve the performance result in face recognition. Fuzzy logic has proved to be a tool that can improve the performance of the existing system